Instructions to use microsoft/Florence-2-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use microsoft/Florence-2-large with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="microsoft/Florence-2-large", trust_remote_code=True)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("microsoft/Florence-2-large", trust_remote_code=True)
model = AutoModelForImageTextToText.from_pretrained("microsoft/Florence-2-large", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use microsoft/Florence-2-large with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "microsoft/Florence-2-large"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/Florence-2-large",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/microsoft/Florence-2-large

SGLang

How to use microsoft/Florence-2-large with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "microsoft/Florence-2-large" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/Florence-2-large",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "microsoft/Florence-2-large" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/Florence-2-large",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use microsoft/Florence-2-large with Docker Model Runner:
```
docker model run hf.co/microsoft/Florence-2-large
```

Fix modeling code (typos/bugs)

#12

by Xenova HF Staff - opened Jun 21, 2024

base: refs/heads/main

←

from: refs/pr/12

Discussion Files changed

-3

Files changed (1) hide show

modeling_florence2.py +9 -3

modeling_florence2.py CHANGED Viewed

@@ -2240,6 +2240,10 @@ class Florence2Seq2SeqLMOutput(ModelOutput):
     decoding.
     Args:
         last_hidden_state (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`):
             Sequence of hidden-states at the output of the last layer of the decoder of the model.
@@ -2288,7 +2292,8 @@ class Florence2Seq2SeqLMOutput(ModelOutput):
             image_hidden_states of the model produced by the vision encoder
     """
     last_hidden_state: torch.FloatTensor = None
     past_key_values: Optional[Tuple[Tuple[torch.FloatTensor]]] = None
     decoder_hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
@@ -2297,6 +2302,7 @@ class Florence2Seq2SeqLMOutput(ModelOutput):
     encoder_last_hidden_state: Optional[torch.FloatTensor] = None
     encoder_hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
     encoder_attentions: Optional[Tuple[torch.FloatTensor, ...]] = None
 FLORENCE2_START_DOCSTRING = r"""
@@ -2527,7 +2533,6 @@ class Florence2ForConditionalGeneration(Florence2PreTrainedModel):
     def __init__(self, config: Florence2Config):
         super().__init__(config)
         assert config.vision_config.model_type == 'davit', 'only DaViT is supported for now'
-        del config.vision_config.model_type
         self.vision_tower = DaViT.from_config(config=config.vision_config)
         # remove unused layers
         del self.vision_tower.head
@@ -2731,7 +2736,8 @@ class Florence2ForConditionalGeneration(Florence2PreTrainedModel):
                 image_features = self._encode_image(pixel_values)
                 inputs_embeds, attention_mask = self._merge_input_ids_with_image_features(image_features, inputs_embeds)
-        attention_mask = attention_mask.to(inputs_embeds.dtype)
         outputs = self.language_model(
             attention_mask=attention_mask,
             labels=labels,

     decoding.
     Args:
+        loss (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided):
+            Language modeling loss.
+        logits (`torch.FloatTensor` of shape `(batch_size, sequence_length, config.vocab_size)`):
+            Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
         last_hidden_state (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`):
             Sequence of hidden-states at the output of the last layer of the decoder of the model.
             image_hidden_states of the model produced by the vision encoder
     """
+    loss: Optional[torch.FloatTensor] = None
+    logits: torch.FloatTensor = None
     last_hidden_state: torch.FloatTensor = None
     past_key_values: Optional[Tuple[Tuple[torch.FloatTensor]]] = None
     decoder_hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
     encoder_last_hidden_state: Optional[torch.FloatTensor] = None
     encoder_hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
     encoder_attentions: Optional[Tuple[torch.FloatTensor, ...]] = None
+    image_hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
 FLORENCE2_START_DOCSTRING = r"""
     def __init__(self, config: Florence2Config):
         super().__init__(config)
         assert config.vision_config.model_type == 'davit', 'only DaViT is supported for now'
         self.vision_tower = DaViT.from_config(config=config.vision_config)
         # remove unused layers
         del self.vision_tower.head
                 image_features = self._encode_image(pixel_values)
                 inputs_embeds, attention_mask = self._merge_input_ids_with_image_features(image_features, inputs_embeds)
+        if inputs_embeds is not None:
+            attention_mask = attention_mask.to(inputs_embeds.dtype)
         outputs = self.language_model(
             attention_mask=attention_mask,
             labels=labels,